• Journal of the Korean Data and Information Science Society
• /
• v.22 no.1
• /
• pp.107-113
• /
• 2011

We present methods for studying the log-density ratio, which allow us to select which predictors are needed, and how they should be included in the logistic regression model. Under multivariate normal distributional assumptions, we investigate the form of the log-density ratio as a function of many predictors. The linear, quadratic and crossproduct terms are required in general. If two covariance matrices are equal, then the crossproduct and quadratic terms are not needed. If the variables are uncorrelated, we do not need the crossproduct terms, but we still need the linear and quadratic terms.

• Journal of applied mathematics & informatics
• /
• v.28 no.1_2
• /
• pp.515-521
• /
• 2010

In multivariate analysis, the inversion formula of the Stieltjes transform is used to find the density of a spectral distribution of random matrices of sample covariance type. Let $B_n\;=\;\frac{1}{N}Y_nY_n^TT_n$ where $Y_n\;=\;[Y_{ij}]_{n\;{\times}\;N}$ is with independent, identically distributed entries and $T_n$ is an $n\;{\times}\;n$ symmetric non-negative definite random matrix independent of the $Y_{ij}$'s. In the present paper, using the inversion formula of the Stieltjes transform, we will find that the limiting distribution of $B_n$ has a continuous density function away from zero.

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.584-586
• /
• 1997

The orthogonal polynomials have been widely employed to solve control problems, but the LQG(linear quadratic gaussian) problem remains unsolved. In this paper, we obtained the solutions of Riccati equation and covariance matrix Riccati equation by two point boundary problem and matrix fraction method using BPF(Block Pulse Function), respectively. This solutions are solved the problem of the LQG controller design.

• International Journal of Reliability and Applications
• /
• v.18 no.2
• /
• pp.65-82
• /
• 2017

Abstract. Camilo Dagum proposed several variants of a new model for the size distribution of personal income in a series of papers in the 1970s. He traced the genesis of the Dagum distributions in applied economics and points out parallel developments in several branches of the applied statistics literature. The main aim of this paper is to define a bivariate Dagum distribution so that the marginals have Dagum distributions. It is observed that the joint probability density function and the joint cumulative distribution function can be expressed in closed forms. Several properties of this distribution such as marginals, conditional distributions and product moments have been discussed. The maximum likelihood estimates for the unknown parameters of this distribution and their approximate variance-covariance matrix have been obtained. Some simulations have been performed to see the performances of the MLEs. One data analysis has been performed for illustrative purpose.

• Journal of the Semiconductor & Display Technology
• /
• v.11 no.3
• /
• pp.19-25
• /
• 2012

The accuracy of Shape From Focus (SFF) technique depends on the quality of the focus measurements which are computed through a focus measure operator. In this paper, we introduce a new approach to estimate 3D shape of an object based on Gaussian process regression. First, initial depth is estimated by applying a conventional focus measure on image sequence and maximizing it in the optical direction. In second step, input feature vectors consisting of eginvalues are computed from 3D neighborhood around the initial depth. Finally, by utilizing these features, a latent function is developed through Gaussian process regression to estimate accurate depth. The proposed approach takes advantages of the multivariate statistical features and covariance function. The proposed method is tested by using image sequences of various objects. Experimental results demonstrate the efficacy of the proposed scheme.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.10 no.4
• /
• pp.53-66
• /
• 1990

Rainfall is a phenomenon that shows a high variability both in space and time, Hy drologists are usually interested in the description of spatial distribution of rainfall over watershed. The theory of Kriging, generalized covariance technique using nonstationary mean in the regions under orographic effect, was chosen to construct random surface of total storm depth. For the constructed random surface, the double Fourier analysis of the total storm depths was performed, and the principal harmonics of storm were determined. The local component, or storm residuals was obtained by subtracting the periodic component of the storm from total storm depths. It is assumed that the residuals are a sample function of a homogeneous random field. This random field can be characterized by an isotropic one dimensional autocorrelation function or its corresponding spectral density function. Under this assumption, this study proposed a theorectical model for spectral density function adapted to two watersheds.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.

• Korean Journal of Remote Sensing
• /
• v.1 no.1
• /
• pp.5-27
• /
• 1985

A hill-sliding technique was devised to extract Gaussian clusters from the multivariate probability density estimates of sample data for the first step of iterative unsupervised classification. The underlying assumption in this approach was that each cluster possessed a unimodal normal distribution. The key idea was that a clustering function proposed could distinguish elements of a cluster under formation from the rest in the feature space. Initial clusters were extracted one by one according to the hill-sliding tactics. A dimensionless cluster compactness parameter was proposed as a universal measure of cluster goodness and used satisfactorily in test runs with Landsat multispectral scanner (MSS) data. The normalized divergence, defined by the cluster divergence divided by the entropy of the entire sample data, was utilized as a general separability measure between clusters. An overall clustering objective function was set forth in terms of cluster covariance matrices, from which the cluster compactness measure could be deduced. Minimal improvement of initial data partitioning was evaluated by this objective function in eliminating scattered sparse data points. The hill-sliding clustering technique developed herein has the potential applicability to decomposition of any multivariate mixture distribution into a number of unimodal distributions when an appropriate diatribution function to the data set is employed.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.16 no.1
• /
• pp.14-26
• /
• 2011

Surface currents were observed by high-frequency (HF) radars off the Keum River estuary from December 2008 to February 2009. The dataset of observed surface currents had data gaps due to the interference of electromagnetic waves and the deteriorating weather conditions. To fill the data gaps an optimal interpolation procedure was developed. The characteristics of spatial correlation in the surface currents off the Keum River estuary were investigated and the spatial data gaps were filled using the optimal interpolation. Then, the temporal and spatial distribution of the interpolated surface currents and the patterns of interpolation error were examined. The correlation coefficients between the surface currents in the coastal region were higher than 0.7 because tidal currents dominate the surface circulation. The sample data covariance matrix (C), spatially averaged covariance matrix with localization ($C^G_{sm}$) and covariance matrix fitted by an exponential function ($C_{ft}$) were used to interpolate the original dataset. The optimal interpolation filled the data gaps and suppressed the spurious data with spikes in the time series of surface current speed so that the variance of the interpolated time series was smaller than that of the original data. When the spatial data coverage was larger (smaller) than 70% of the region, the interpolation error produced by $C^G_{sm}$ ($C_{ft}$) was smaller compared with that by C.

• Proceedings of the Korea Water Resources Association Conference
• /
• 1992.07a
• /
• pp.411-418
• /
• 1992

The purpose of this study is to develop dynamic-stochastic models that can forecast the inflow into reservoir during low/drought periods and flood periods. For the formulation of the models, the discrete transfer function is utilized to construct the deterministic characteristics, and the ARIMA model is utilized to construct the stochastic characteristics of residuals. The stochastic variations and structures of time series on hydrological data are examined by employing the auto/cross covariance function and auto/cross correlation function. Also, general modeling processes and forecasting method are used the model building methods of Box and Jenkins. For the verifications and applications of the developed models, the Chungju multi-purpose reservoir which is located in the South Han river systems is selected. Input data required are the current and past reservoir inflow and Yungchun water levels. In order to transform the water level at Yungchon into streamflows, the water level-streamflows rating curves at low/drought periods and flood periods are estimated. The models are calibrated with the flood periods of 1988 and 1989 and hourly data for 1990 flood are analyzed. Also, for the low/drought periods, daily data of 1988 and 1989 are calibrated, and daily data for 1989 are analyzed.